From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx1.redhat.com ([209.132.183.28]:51427 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754197AbdAKCm2 (ORCPT ); Tue, 10 Jan 2017 21:42:28 -0500 Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (Mac OS X Mail 10.2 \(3259\)) Subject: Re: [PATCH v2] ceph/iov_iter: fix bad iov_iter handling in ceph splice codepaths From: "Yan, Zheng" In-Reply-To: <1484053051-23685-1-git-send-email-jlayton@redhat.com> Date: Wed, 11 Jan 2017 10:42:18 +0800 Cc: Al Viro , Sage Weil , Ilya Dryomov , ceph-devel@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, "Zhu, Caifeng" Content-Transfer-Encoding: 8BIT Message-Id: References: <1483727016-343-1-git-send-email-jlayton@redhat.com> <1484053051-23685-1-git-send-email-jlayton@redhat.com> To: Jeff Layton Sender: linux-fsdevel-owner@vger.kernel.org List-ID: > On 10 Jan 2017, at 20:57, Jeff Layton wrote: > > v2: fix bug in offset handling in iov_iter_pvec_size > > xfstest generic/095 triggers soft lockups in kcephfs. Basically it uses > fio to drive some I/O via vmsplice ane splice. Ceph then ends up trying > to access an ITER_BVEC type iov_iter as a ITER_IOVEC one. That causes it > to pick up a wrong offset and get stuck in an infinite loop while trying > to populate the page array. dio_get_pagev_size has a similar problem. > > To fix the first problem, add a new iov_iter helper to determine the > offset into the page for the current segment and have ceph call that. > I would just replace dio_get_pages_alloc with iov_iter_get_pages_alloc, > but that will only return a single page at a time for ITER_BVEC and > it's better to make larger requests when possible. > > For the second problem, we simply replace it with a new helper that does > what it does, but properly for all iov_iter types. > > Since we're moving that into generic code, we can also utilize the > iterate_all_kinds macro to simplify this. That means that we need to > rework the logic a bit since we can't advance to the next vector while > checking the current one. > > Link: http://tracker.ceph.com/issues/18130 > Cc: "Zhu, Caifeng" > Signed-off-by: Jeff Layton > --- > fs/ceph/file.c | 28 ++------------------- > include/linux/uio.h | 2 ++ > lib/iov_iter.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++++++++ > 3 files changed, 75 insertions(+), 26 deletions(-) > > diff --git a/fs/ceph/file.c b/fs/ceph/file.c > index f633165f3fdc..0cd9fc68a04e 100644 > --- a/fs/ceph/file.c > +++ b/fs/ceph/file.c > @@ -35,29 +35,6 @@ > */ > > /* > - * Calculate the length sum of direct io vectors that can > - * be combined into one page vector. > - */ > -static size_t dio_get_pagev_size(const struct iov_iter *it) > -{ > - const struct iovec *iov = it->iov; > - const struct iovec *iovend = iov + it->nr_segs; > - size_t size; > - > - size = iov->iov_len - it->iov_offset; > - /* > - * An iov can be page vectored when both the current tail > - * and the next base are page aligned. > - */ > - while (PAGE_ALIGNED((iov->iov_base + iov->iov_len)) && > - (++iov < iovend && PAGE_ALIGNED((iov->iov_base)))) { > - size += iov->iov_len; > - } > - dout("dio_get_pagevlen len = %zu\n", size); > - return size; > -} > - > -/* > * Allocate a page vector based on (@it, @nbytes). > * The return value is the tuple describing a page vector, > * that is (@pages, @page_align, @num_pages). > @@ -71,8 +48,7 @@ dio_get_pages_alloc(const struct iov_iter *it, size_t nbytes, > struct page **pages; > int ret = 0, idx, npages; > > - align = (unsigned long)(it->iov->iov_base + it->iov_offset) & > - (PAGE_SIZE - 1); > + align = iov_iter_single_seg_page_offset(it); > npages = calc_pages_for(align, nbytes); > pages = kmalloc(sizeof(*pages) * npages, GFP_KERNEL); > if (!pages) { > @@ -927,7 +903,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, > } > > while (iov_iter_count(iter) > 0) { > - u64 size = dio_get_pagev_size(iter); > + u64 size = iov_iter_pvec_size(iter); > size_t start = 0; > ssize_t len; > > diff --git a/include/linux/uio.h b/include/linux/uio.h > index 6e22b544d039..46fdfff3d7d6 100644 > --- a/include/linux/uio.h > +++ b/include/linux/uio.h > @@ -83,6 +83,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, > void iov_iter_advance(struct iov_iter *i, size_t bytes); > int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); > size_t iov_iter_single_seg_count(const struct iov_iter *i); > +size_t iov_iter_single_seg_page_offset(const struct iov_iter *i); > size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, > struct iov_iter *i); > size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, > @@ -93,6 +94,7 @@ size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); > size_t iov_iter_zero(size_t bytes, struct iov_iter *); > unsigned long iov_iter_alignment(const struct iov_iter *i); > unsigned long iov_iter_gap_alignment(const struct iov_iter *i); > +size_t iov_iter_pvec_size(const struct iov_iter *i); > void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, > unsigned long nr_segs, size_t count); > void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *kvec, > diff --git a/lib/iov_iter.c b/lib/iov_iter.c > index 6b415b5a100d..b8fa377b0cef 100644 > --- a/lib/iov_iter.c > +++ b/lib/iov_iter.c > @@ -745,6 +745,24 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i) > } > EXPORT_SYMBOL(iov_iter_single_seg_count); > > +/* Return offset into page for current iov_iter segment */ > +size_t iov_iter_single_seg_page_offset(const struct iov_iter *i) > +{ > + size_t base; > + > + if (i->type & ITER_PIPE) > + base = i->pipe->bufs[i->idx].offset; > + else if (i->type & ITER_BVEC) > + base = i->bvec->bv_offset; > + else if (i->type & ITER_KVEC) > + base = (size_t)i->kvec->iov_base; > + else > + base = (size_t)i->iov->iov_base; > + > + return (base + i->iov_offset) & (PAGE_SIZE - 1); > +} > +EXPORT_SYMBOL(iov_iter_single_seg_page_offset); > + > void iov_iter_kvec(struct iov_iter *i, int direction, > const struct kvec *kvec, unsigned long nr_segs, > size_t count) > @@ -830,6 +848,59 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i) > } > EXPORT_SYMBOL(iov_iter_gap_alignment); > > +/** > + * iov_iter_pvec_size - find length of page aligned iovecs in iov_iter > + * @i: iov_iter to in which to find the size > + * > + * Some filesystems can stitch together multiple iovecs into a single > + * page vector when both the previous tail and current base are page > + * aligned. This function discovers the length that can fit in a single > + * pagevec and returns it. > + */ > +size_t iov_iter_pvec_size(const struct iov_iter *i) > +{ > + size_t size = i->count; > + size_t pv_size = 0; > + bool contig = false, first = true; > + > + if (!size) > + return 0; > + > + /* Pipes are naturally aligned for this */ > + if (unlikely(i->type & ITER_PIPE)) > + return size; > + > + /* > + * An iov can be page vectored when the current base and previous > + * tail are both page aligned. Note that we don't require that the > + * initial base in the first iovec also be page aligned. > + */ > + iterate_all_kinds(i, size, v, > + ({ > + if (first || (contig && PAGE_ALIGNED(v.iov_base))) { > + pv_size += v.iov_len; > + first = false; > + contig = PAGE_ALIGNED(v.iov_base + v.iov_len); > + }; 0; > + }), > + ({ > + if (first || (contig && v.bv_offset == 0)) { > + pv_size += v.bv_len; > + first = false; > + contig = PAGE_ALIGNED(v.bv_offset + v.bv_len); > + } > + }), > + ({ > + if (first || (contig && PAGE_ALIGNED(v.iov_base))) { > + pv_size += v.iov_len; > + first = false; > + contig = PAGE_ALIGNED(v.iov_base + v.iov_len); > + } > + })) > + return pv_size; > +} > +EXPORT_SYMBOL(iov_iter_pvec_size); > + > static inline size_t __pipe_get_pages(struct iov_iter *i, > size_t maxsize, > struct page **pages, Reviewed-by: Yan, Zheng > -- > 2.7.4 >